Text Generation
PEFT
Safetensors
English
lora
qwen3
uncertainty
calibration
abstention
retrieval-augmented-generation
Instructions to use Sentovara/Sentinel-S1-Qwen3-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Sentovara/Sentinel-S1-Qwen3-8B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "Sentovara/Sentinel-S1-Qwen3-8B") - Notebooks
- Google Colab
- Kaggle
Download eval/modelq.py from Sentovara/Sentinel-S1-Qwen3-8B: direct link, hf CLI and curl.
- Browser
- Download file 256 Bytes
-
https://huggingface.co/Sentovara/Sentinel-S1-Qwen3-8B/resolve/main/eval/modelq.py
- Command line
-
hf download hf://Sentovara/Sentinel-S1-Qwen3-8B/eval/modelq.py
-
curl -L -o modelq.py https://huggingface.co/Sentovara/Sentinel-S1-Qwen3-8B/resolve/main/eval/modelq.py
256 Bytes
| """Job Q base model (owner GO 15 Nov 2026 08:33 UK): Qwen3 8B, Alibaba Qwen team, Apache 2.0, pinned revision. Thinking mode off throughout.""" | |
| MODELQ, REVQ = "Qwen/Qwen3-8B", "b968826d9c46dd6066d109eabc6255188de91218" | |
| CHAT_KW = {"enable_thinking": False} | |